© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 44505
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate violence or aggressive actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.01
    2:0.05
    3:0.05
    4:0.08
    5:0.03
    6:0.45
    7:0.09
    8:0.03
    9:0.03
    10:0.06
    11:0.04
    Negative Logits
    ource
    -1.79
    ategories
    -1.48
    DAY
    -1.41
    XM
    -1.38
    Lower
    -1.37
    taboola
    -1.37
    FORMATION
    -1.36
    Low
    -1.30
     Attribution
    -1.28
    veyard
    -1.27
    POSITIVE LOGITS
    dash
    1.48
    adesh
    1.34
    mith
    1.30
    adder
    1.26
    rison
    1.24
    wall
    1.21
    ush
    1.20
    har
    1.19
     resusc
    1.19
     dams
    1.18
    Activations Density 0.003%

    No Known Activations